Multi-tiered transportation identification system

Abstract

A system for identifying an aspect of interest on a vehicle that includes a local AI system that can analyze sensor data from an on-site sensor to make an attempt to identify the aspect of interest according to first criterion. The aspect of interest can be information printed on the vehicle and/or on a seal of the vehicle. If the local AI system is unable to identify and validate the information on the first effort, it can consult with a central/global AI system that can leverage its own database and other local systems at other locations for subsequent attempts at identifying and validating the aspects of interest.

What is claimed is: 
     
       1. A method of training a networked system to identify an aspect of a target, comprising:
 using a first sensor to derive first sensor data from an environment having the target; 
 using a local AI system executed by at least one processor to analyze the first sensor data to make a first effort to identify the aspect of the target; 
 determining whether the first effort satisfies a first criterion; and 
 in the event that the first effort fails to satisfy the first criterion: 
 providing at least some of the first sensor data as an input to a global AI system; and 
 using the global AI system executed by at least one second processor to make a second effort to identify the aspect of the target using at least one of the first criterion or a second criterion. 
 
     
     
       2. The method of  claim 1 , further comprising: in the event that the second effort satisfies the second criterion, providing information to the local AI system to assist the local AI system in a future identification of the aspect of the target. 
     
     
       3. The method of  claim 1 , wherein the target is a seal, and the aspect is a sequence of digits displayed on the seal. 
     
     
       4. The method of  claim 1 , wherein the target comprises a seal affixed to a motor vehicle. 
     
     
       5. The method of  claim 4 , wherein the motor vehicle is moving while the local AI system is making the first effort to identify the aspect of the target. 
     
     
       6. The method of  claim 1 , wherein at least one of the first and second criterion comprises a reliability criterion. 
     
     
       7. The method of  claim 1 , wherein at least one of the first and second criterion comprises an accuracy criterion. 
     
     
       8. The method of  claim 1 , wherein the environment at least partially obscures the target. 
     
     
       9. The method of  claim 3 , wherein the local AI system is located at a first location and wherein a vehicle to which the seal is affixed is located at the first location, the method further comprising:
 determining, by the global AI system, that the sequence of digits was unreadable; 
 consulting, by the global AI system, with a second local AI system, wherein the second local AI system corresponds to a second location from which the vehicle came; 
 receiving, by the global AI system, a response from the second local AI system that confirms the sequence of digits was successfully read at the second location; and 
 determining, by the global AI system, that the seal was tampered with based on the successful reading of the sequence of digits at the second location and the unsuccessful reading of the sequence of digits at the first location.